Product review attribute-level emotion classification method based on rules and neural networks

A neural network and product review technology, applied in the field of attribute-level sentiment analysis for product reviews, can solve problems such as high labor costs, low efficiency of emotion judgment, and inability to fully express the emotional relationship between attribute words and contextual semantics, so as to improve accuracy sexual effect

Active Publication Date: 2018-03-30
NANJING UNIV OF SCI & TECH
View PDF6 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional method uses artificial rules to judge attribute-level emotions, which requires high labor costs and low efficiency of emotion judgments
In recent years, some scholars have proposed to solve this problem based on ma

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Product review attribute-level emotion classification method based on rules and neural networks
  • Product review attribute-level emotion classification method based on rules and neural networks
  • Product review attribute-level emotion classification method based on rules and neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The solution of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0013] A method for attribute-level sentiment classification of product reviews based on rules and neural networks, characterized in that it comprises the following steps:

[0014] Step 1. Obtain comment data, perform Chinese word segmentation and stop word filtering on the comment text, specifically:

[0015] Step 1.1, perform HTML parsing on the product review corpus crawled by the web crawler, filter out relevant review texts, and obtain a review text set;

[0016] Step 1.2, use the NLPIR word segmentation system to perform Chinese word segmentation on the product review text;

[0017] Step 1.3. On the basis of the existing stop word list, add English characters, numbers, and punctuation marks to construct a stop word list suitable for Chinese product review texts, and perform stop word filtering on the words after Chinese w...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a product review attribute-level emotion classification method based on rules and neural networks. The method includes the steps: firstly, acquiring review data and filtering Chinese participles and stop words from a review text; secondly, screening a product attribute set by the aid of a rule template, building a <attribute and review> sample set, performing emotion tagging on the attribute of each review, and building a <attribute, review and emotion> training set; building a neural network emotion classification model based on bilateral attention, and training the model by the aid of the training set; finally, filtering Chinese participles and stop words from testing data, screening a product attribute set, building a <attribute and review> testing set, and performing emotion classification by the aid of an emotion classification model. According to the method, attribute emotion category forecasting accuracy can be greatly and effectively improved by the aidof context information of attributes in the reviews.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an attribute-level sentiment analysis method for product reviews. Background technique [0002] Under the premise of the rapid development of the Internet, e-commerce, as an emerging field of the Internet, has achieved considerable development. More and more users are purchasing online commodities through different e-commerce websites, resulting in massive consumer purchase reviews. Faced with a large number of shopping reviews, it is impossible for consumers to read them one by one, and merchants are eager to analyze and sort out product reviews. Opinion mining and sentiment analysis technology for product reviews are not only academic frontier issues and hot research issues in the field of natural language processing and sentiment analysis, but also important issues to be solved in application fields such as e-commerce shopping platforms, which have immeasurable applicat...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/2413
Inventor 夏睿郑士梁
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap